Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2603 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.3177. Min Act: -0.0000

Data Index: 1591465 (Python Code)

Max Activating Token Index: 256

Text #1

Max Range: 3.3177. Min Range: -3.3177

Max Act: 2.0600. Min Act: -0.0000

Data Index: 1611892 (Python Code)

Max Activating Token Index: 746

Text #2

Max Range: 3.3177. Min Range: -3.3177

Max Act: 2.4120. Min Act: -0.0000

Data Index: 1594069 (Python Code)

Max Activating Token Index: 122

Text #3

Max Range: 3.3177. Min Range: -3.3177

Max Act: 2.0206. Min Act: -0.0000

Data Index: 1413852 (Python Code)

Max Activating Token Index: 847

Text #4

Max Range: 3.3177. Min Range: -3.3177

Max Act: 2.2487. Min Act: -0.0000

Data Index: 1368526 (Python Code)

Max Activating Token Index: 629

Text #5

Max Range: 3.3177. Min Range: -3.3177

Max Act: 2.4461. Min Act: -0.0000

Data Index: 1645602 (Python Code)

Max Activating Token Index: 649

Text #6

Max Range: 3.3177. Min Range: -3.3177

Max Act: 2.0717. Min Act: -0.0000

Data Index: 1483195 (Python Code)

Max Activating Token Index: 428

Text #7

Max Range: 3.3177. Min Range: -3.3177

Max Act: 2.0759. Min Act: -0.0000

Data Index: 1570076 (Python Code)

Max Activating Token Index: 688

Text #8

Max Range: 3.3177. Min Range: -3.3177

Max Act: 2.0195. Min Act: -0.0000

Data Index: 1544589 (Python Code)

Max Activating Token Index: 98

Text #9

Max Range: 3.3177. Min Range: -3.3177

Max Act: 1.7809. Min Act: -0.0000

Data Index: 1586696 (Python Code)

Max Activating Token Index: 674

Text #10

Max Range: 3.3177. Min Range: -3.3177

Max Act: 1.7614. Min Act: -0.0000

Data Index: 1370847 (Python Code)

Max Activating Token Index: 954

Text #11

Max Range: 3.3177. Min Range: -3.3177

Max Act: 1.7545. Min Act: -0.0000

Data Index: 1615100 (Python Code)

Max Activating Token Index: 629

Text #12

Max Range: 3.3177. Min Range: -3.3177

Max Act: 1.8324. Min Act: -0.0000

Data Index: 1580141 (Python Code)

Max Activating Token Index: 858

Text #13

Max Range: 3.3177. Min Range: -3.3177

Max Act: 1.6730. Min Act: -0.0000

Data Index: 1553565 (Python Code)

Max Activating Token Index: 961

Text #14

Max Range: 3.3177. Min Range: -3.3177

Max Act: 1.6170. Min Act: -0.0000

Data Index: 1499694 (Python Code)

Max Activating Token Index: 11

Text #15

Max Range: 3.3177. Min Range: -3.3177

Max Act: 1.8111. Min Act: -0.0000

Data Index: 1528952 (Python Code)

Max Activating Token Index: 380

Text #16

Max Range: 3.3177. Min Range: -3.3177

Max Act: 1.7803. Min Act: -0.0000

Data Index: 1528855 (Python Code)

Max Activating Token Index: 99

Text #17

Max Range: 3.3177. Min Range: -3.3177

Max Act: 1.5621. Min Act: -0.0000

Data Index: 503881 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 3.3177. Min Range: -3.3177

Max Act: 1.7485. Min Act: -0.0000

Data Index: 1581808 (Python Code)

Max Activating Token Index: 828

Text #19

Max Range: 3.3177. Min Range: -3.3177

Max Act: 1.5908. Min Act: -0.0000

Data Index: 1652040 (Python Code)

Max Activating Token Index: 232